AWS EC2 Instance

g5.16xlarge

The g5.16xlarge is a GPU-accelerated AWS EC2 instance with 64 vCPUs and 256 GB of memory, 1 A10G GPU, powered by AMD. Ideal for deep learning training, high-performance computing, and GPU-intensive inference workloads. On-demand pricing starts at $4.0960/hr in us-east-1.

Price History

Pricing by Region

Region On-Demand Spot Reserved 1Y
us-east-1$4.096$1.710$3.071
us-east-2$4.096$0.572$3.071
us-west-2$4.096$3.071
eu-north-1$4.344$0.920$3.257
ca-central-1$4.548$3.410
eu-west-1$4.572$1.235$3.428
il-central-1$4.801$0.480$3.599
ap-south-1$4.918$3.688
me-central-1$5.024$3.767
ap-northeast-2$5.037$0.515$3.776
eu-central-1$5.122$1.822$3.840
eu-west-2$5.199$3.898
ap-southeast-2$5.326$1.648$3.993
ap-southeast-3$5.733$0.573$4.298
ap-northeast-1$5.940$4.454
ap-east-1$6.306$4.728
sa-east-1$6.962$5.220

Frequently Asked Questions

What is the g5.16xlarge?
The g5.16xlarge is a GPU-accelerated AWS EC2 instance with 64 vCPUs and 256 GB of memory, 1 A10G GPU, powered by AMD. Ideal for deep learning training, high-performance computing, and GPU-intensive inference workloads. On-demand pricing starts at $4.0960/hr in us-east-1.
What is the cheapest region for g5.16xlarge?
us-east-1 at $4.096/hr on-demand.
How much does g5.16xlarge cost per month?
Starting at $2990.08/mo on-demand in us-east-1, or $350.47/mo with spot pricing.

Run a free assessment to identify overprovisioned workloads, idle capacity, and your potential savings, in minutes.

Most clusters are overprovisioned.
Let's prove yours is.